Paper: An Evaluation Framework for Plagiarism Detection

ACL ID C10-2115
Title An Evaluation Framework for Plagiarism Detection
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010

We present an evaluation framework for plagiarism detection. 1 The framework provides performance measures that ad- dress the specifics of plagiarism detec- tion, and the PAN-PC-10 corpus, which contains 64 558 artificial and 4 000 sim- ulated plagiarism cases, the latter gener- ated via Amazon’s Mechanical Turk. We discuss the construction principles behind the measures and the corpus, and we com- pare the quality of our corpus to exist- ing corpora. Our analysis gives empirical evidence that the construction of tailored training corpora for plagiarism detection can be automated, and hence be done on a large scale.